In this work, an algorithm of enhanced grey wolf optimization (EGWO) is developed to resolve the scheduling problem of a power system, which is having thermal, hydro, wind, and solar power plants with a battery energy storing system (BESS). The planning period covers 24 equal intervals of a day. In this scheduling problem, the impact on valve point loading of thermal plants, the time coupling effect in cascaded reservoirs of hydro units, and various constraints imposed on the power network are taken into consideration. The grey wolf optimization (GWO) technique is used, which is framed on the group attitude of grey wolves such as governance ranking and hunting activity. In this proposed algorithm, GWO algorithm is enhanced using three techniques. First, the quasi-oppositional learning approach is exploited to obtain the optimal solution quickly. Second, the elite mutation operator is applied to maximize the diversity of the swarm. Finally, by implementing the elastic-ball strategy, infeasible solutions are modified into feasible one. The potential of the EGWO technique is ascertained by employing it in two experimental settings. From the simulation outcome, it is inferred that the implemented technique bestows less operating cost with minimal computation time as compared to other evolutionary techniques.

The increasing demand for renewable energy has forced the researchers to lay importance on studying the behavior of these sources by monitoring the operational data and performing data analysis. The application of data analytics to renewable energy is one of the most powerful methods to maintain the system's reliability and stability. As the power system becomes more complex the necessity to perform data analytics also increases. When data analytic techniques are applied to solar energy generations through Photovoltaic (PV) dataset, the possible behavior of PV generation performance which is affected by changes in environmental conditions can be predicted and further analytical approaches allow us to detect possible PV panel and inverter failures. This paper is an attempt towards applying the intelligent data analytics approaches to solar PV generation of a real-time photovoltaic plant. The main purpose of the data analytics platform is to analyze the energy yield, assess the PV system performance, and forecast solar PV generation. In this article, Long Short-Term Memory (LSTM) machine learning model is developed to assess and interpret the available information from the gathered data of the PV plant. The proposed model is a sequence-to-sequence regression-based forecasting model which performs time series forecasting in a real-time 100 kW PV plant in the University building of SRM Institute of Science and Technology, Kattankulathur, Tamilnadu.

Jackfruit (Artocarpus heterophyllus), a tropical fruit renowned for its diverse culinary uses, necessitates identifying the optimal growth stage to ensure superior flavor and texture. This research investigates employing deep learning techniques, particularly convolutional neural networks (CNNs), for accurately detecting jackfruit growth stages. Despite the challenge posed by the nuanced visual differences among fruits at various maturity stages, a meticulously curated dataset of labeled jackfruit images was developed in collaboration with experts, utilizing the BBCH scale. This dataset facilitated training and evaluation. A modified version of the Places 365 GoogLeNet CNN model was proposed for classifying four distinct growth stages of jackfruit, compared with a state-of-the-art CNN model. The trained models demonstrated varying levels of accuracy in classification. Furthermore, the proposed CNN model was trained and tested using original and augmented images, achieving an impressive overall validation accuracy of 90%. These results underscore the efficacy of deep learning in automating the detection of growth stages, offering promising implications for quality control and decision-making in jackfruit production and distribution.

DC microgrids (MGs) are gaining popularity as efficient solutions for integrating diverse energy resources. Traditionally, droop control has been widely used as a decentralized control method for distributing power in DC MGs. This paper introduces a new approach by implementing an Adaptive Dropping-based Split range control using an Proportional-integral controller which involves the use of two valves, a big valve and a small valve, to effectively control the underlying process and also explores the topology and operational characteristics of an adaptive drooping-based Split-Pi pulse generated fed DC-DC power converter. The Split-Pi pulse generated fed DC-DC converter was utilized to obtain results for battery charging or EV applications. Feed-forward control is used to show how to regulate the gain of the Split-Pi pulse-generated fed DC-DC converter by directly computing the necessary converter gain. In this paper PV inputs converter based on the Adaptive Drooping technique is developed to make a simulation circuit for an input of $12{{\ V}}$ from the $\text{PV}$ panel and an output voltage of $42{{\ V}}$ across the load for the battery charging and discharging circuits. Utilizing Split-PI in droop control enhances the stability of the microgrid system in comparison to high gain. Compared to the traditional PI controller, the dynamic response of the microgrid system is enhanced, resulting in increased stability.

Photovoltaic systems are growing in popularity to generate clean electrical energy. Nevertheless, because of minimal efficiency, researchers have sought methods for enhancing its productivity. Maximum Power Point Trackers (MPPT) allow us to extract the most energy from PV panels that can be produced. It involves an algorithm to calculate the Maximum Power Point (MPP). The most commonly used MPPT methodologies, Incremental Conductance (I-C) and Perturb and Observe (P-O) provide long-term reliability for consistent environmental conditions, although tracking becomes complicated for varying environmental patterns. It was proved that ANN (Artificial Neural network) can track MPP with a small transient time and less ripple. Subsequently, to achieve the ideal MPP, the ANN method must be extensively adjusted. For desired performance, the number of hidden layers and neurons in every hidden layer must be properly chosen. Thus, the Seagull Optimisation (SO) algorithm is employed to optimise ANN in this work. Its capacity to perform is compared with that of P-O, ANN, and PSO. (Particle Swarm Optimization) for constant and varying climatic conditions.

Phasor Measurement Units(PMUs), play a pivotal role in controlling, monitoring, and protection of electrical networks. Achieving complete observability while minimizing the number of PMUs installed is a key consideration during PMU placement. This paper focus on Genetic Algorithm-based approaches for optimizing PMU placement to ensure full observability. The proposed technique is simulated using MATLAB on IEEE-57 bus systems. In addition, the obtained result is compared with the results of traditional methods.

Renewable energy sources are becoming more and more important as a sustainable energy source due to rising energy demand. Wind power is a major renewable energy source, but its integration into the traditional system presents control and stability challenges. To overcome these issues, an efficient scheme for optimal integration of wind energy and neural network based Static Var Compensators (SVC) was designed to regulate power flows in a stable manner. At first, using optimization to detect the exact location of the wind source in a standard IEEE-30 bus system. The cost and voltage stability of the bus system are taken into consideration as the objective function. After integration of the wind source, the generation may vary by varying the wind speed thus causing system instability which was reduced by injecting the reactive power. In the suggested work, SVC was included into a weak bus system to provide reactive power as needed to sustain steady power flows. Using a neural network system, which analyzes bus voltage to produce a pulse signal, the SVC control approach was implemented. For every atmospheric condition and fault duration, the suggested model suited the data quite well. The proposed model maintains stability between 0-1, and the performance of the neural network controller is 0.99 accuracy, 0.99 precision, and 0.99 F1_score. The results of the simulation show that SVC with an advanced controller tends to lower voltage fluctuation and improve system stability as compared with the current one.

Packet classification in software-defined network has become more important with the rapid growth of Internet. Existing approaches focused on the data structure algorithms to classify the packets. But the existing algorithms lead to the problem of time budget and fails to accommodate large rule sets. Thus the key task is to design an algorithm for packet classification that inflicts process overhead, and the algorithm should handle large databases of classification rule. These challenging issues are achieved by proposing rectified linear unit deep neural network. The aim of this work is twofold. First various hyper-parameter values are analyzed in order to examine how they affect the packet classification performance of deep neural network; and their performance is compared with that of popular methods, e.g., K-nearest neighbor and support vector machines. The open-source TensorFlow deep learning framework with the support of NVidia GPU units is used to carry out this work, thus allowing a large number of rules to predict the exact flow. The result shows that the proposed method performs well, and hence, this model is more suitable for large classification rules.

The Critical Clearance Time analysis of an electric power system is crucial in designing the protective devices. The Critical Clearing Time analysis of Wind Energy Conversion System on IEEE 14 bus is done in this work using Power System Analysis Toolbox. Using Time Domain Simulation, the rotor angle stability of the power system is investigated under stable and unstable conditions for determining Critical Clearing Time. A three-phase fault is simulated at various buses to analyze the effect of fault location and critical clearing time on the system stability. The perturbations of the rotor angle are also analyzed during fault and verified whether it satisfies the Fault Ride Through standards.

Cotton is one of the most vital cash crops cultivated around the globe and its yield directly influences the economy and the livelihood of huge number of people associated with it. The major loss of cotton occurs due to damage incurred by microbial pathogens that infect the cotton crop. The course of infection and their effect on the growth and yield of the plant varies depending upon the type of disease. Appropriate treatment for the specific type of disease could prevent the spread of infection and also reduce the use of pesticide that is usually done during the empirical treatment techniques. Identification of the type of cotton plant disease is critical and needs to be done at a faster pace. Image processingbased machine learning approach is found to be a better option for this application. This article deals with development of the machine learning model capable of identifying the different types of cotton plant diseases using image processing. Foliar images of diseased cotton plants are collected from public databases and preprocessing operations like resizing, filtering and contrast enhancement are performed followed by k-means clustering for segmentation of diseased part of the leaf. Image decomposition is performed using discrete wavelet transform with Daubechies wavelet at five levels and the mean, standard deviation, and entropy of the coefficients are used for building the machine learning model. Classification with Artificial Neural Network trained with backpropagation algorithm has a classification accuracy of 97% indicating the veracity of the model. Hence, the developed model could be used as for developing a user-friendly interface that could be tapped for real-time applications.

One among the most crucial parts of green energy systems is thought to be high-gain DC/DC converters. Utilizing an excessive duty cycle, a great deal of high-gain converters are used to enhance the gain of voltage. However, it raises expenses and losses, deteriorates system performance, and results in low efficiency. Combining the good aspects of the high gain converter with a three-port converter is quite advantageous. A DC/DC boost converter that operates with a gain which is high will be discussed here. Applications requiring a high voltage gain and low input voltage, including fuel cell and solar photovoltaic systems, may find usage for this converter. The topology is distinguished by its ease of use, improved gain of voltage, improved efficiency, and continuity of the input current. To enhance system performance, the control logic also incorporates an energy management system. The control methods, which includes energy management and topology's viability was demonstrated using MATLAB/Simulink

This paper proposes an intelligent energy management system in grid-connected microgrid with renewable energy and battery storage systems. The battery charging and discharging strategy is regulated so that the overall energy cost, along with battery degradation cost, is minimized considering the variation in grid tariff, inconsistent renewable power output and changing load demand. The proposed model is developed as an optimization-based problem over a 24-hour horizon using Long Short-Term Memory (LSTM) based forecasting Energy Management-based Model Predictive Control. The proposed model provides information about the renewable power generation and demand for next 24 hours through LSTM based prediction model. The Long Short-Term Memory network is developed for time series forecasting of renewable generation and its performance is compared with other regression models. The Receding Horizon strategy is proposed to reduce the forecasting results of LSTM is fed as inputs to the Model Predictive Control based Energy management system forecasts and enable the implementation of energy management system. The proposed algorithm is developed and implemented in microgrid environment in MATLAB/Simulink 2022b under three case studies and the results claim that the proposed LSTM-MPC control strategy is successful in terms of reducing the grid consumption cost without much degrading the energy storage. The proposed model is also validated in 1kW microgrid hardware setup and promising results are obtained

Smart meter is a customer locality component of modern electrical grid. It is an easy target for the cyber-attacks. Learning algorithm-based intrusion detection system has good performance in various applications. It is a notable mechanism that provides security by early detection of intrusions from the meter traffic communication. The noisy data collected from the sources diminish the functioning of the attack finding algorithms. Thus, the feature selection algorithms are used to enhance the detection ratio of machine learning classifier. In this work, a collaborative method using wrapper-based whale optimization algorithm and filter-based mutual information is used to recognize the informational features. The identified features are feed as input to support vector machine classifier. The standard dataset ADFA-LD is employed to inspect the effectiveness of recommended method. The outputs certified the suitability of selected hybrid method for providing security to smart meter communication network.

Cyber-physical power system (CPPS) has emerged due to the integration of communication, and information advancement in the electrical grid. Owing to the extensive growth of the DC-microgrid (DC-MG) network, and even with the implementation of advanced control, monitoring, and operating methods, these networks remain vulnerable to a range of cyber attacks in the near future. Thus, it is crucial to defend against assaults on these networked cyber-physical systems (CPS). In this work, false data injection (FDI) attacks, time delay attacks, replay attacks, and malware-based attacks are created in the test system and the system performance is measured. These attacks can be identified and recognized by the proposed cyber attack detection methodology based on dynamic watermarking with a Kalman filter for analyzing the terminal current, and load current using smart sensors, actuators, and controllers to eliminate the state of the system. The dynamic signals with watermarking can identify malicious misbehavior from sensors and actuators. This paper also demonstrates how networked systems of sensors and actuators can be secured using the proposed cyber detection approach. The aforementioned cyber attacks are created in the DC-MG test system with four distributed generation units representing four physical nodes in a networked cyber-physical power system created in MATLAB environment version 2023b. The purpose of examining the simulation results for various attacks is to assess the performance of the proposed methodology. The results shows the performance of the proposed strategy can give a more reliable and accurate decision method.

Reducing greenhouse gas emissions and pollution in our environment can be achieved with electric automobiles. Electric Vehicle is highly required to replace the impact of IC engines. The goals include enhancing fuel efficiency, cutting emissions, guaranteeing drivability, and preserving the energy storage system's longevity and current state of charge while taking constraints into account. Power train that is driven by fuel cells, batteries, and super capacitors can offer an economical transportation solution. An effective Energy Management System (EMS) is highly required to distribute power across the power train's components by choosing the right operating modes. This article has discussed the electric vehicle's modeling. An optimized model has been created by taking into account real key parameters. This study compares the actual speed of the vehicle with the input drive speed to determine the optimal performance of an electric car. The initial and final charge of the battery is used to compare the energy consumption value of the electric vehicle. Examined has been the impact of many characteristics on the energy consumption and performance of vehicles.

Electromyographic signals offer details on a muscle activity of a person. In the case of hand movements various combinations of forearm muscles must be activated in order to carry out each gesture, which results in unique electrical patterns. On the other hand, identifying the motion being executed is made possible by the examination of these patterns of muscle activation, which are captured by EMG signals. This article presents a novel implementation on hand gesture classification utilizing Electromyography (EMG) signals recorded through a MYO Thalmic bracelet. The dataset consists of raw data collected from 36 subjects, each executing a series of static hand gestures. The classification model employed for this study is an ensemble of decision trees, achieving an impressive validation accuracy of 98.0% and a test accuracy of 98.1 %. The article outlines the dataset details, recording methodology, and provides an in-depth analysis of the model architecture, hyperparameters, and training results.

Most regions of the world have seen tremendous growth in distributed energy resources, especially photovoltaic (PV) generation. The penetration of PV generation into the power grid is high and hence it has a major impact in power system. The integration of solar PV plant into the power system has both negative as well as positive impacts on transient stability of the power system during faults. In this work, the proposed current amplitude limiting based Fault Ride Through (FRT) control algorithm is implemented in large scale power systems and enhancement of transient stability is also studied in terms of synchronous machine side and grid side parameters namely rotor speed deviation, load angle, relative rotor angle, active and reactive power. The transient stability of large-scale Grid Connected solar PV (GCPV) system is discussed in this article, when the system is incorporated with the proposed FRT control strategy. The large scale GCPV system is said to be stable, if the angular displacement between the machines in the system stays within predetermined limits. The parameters considered for transient analysis on the synchronous machine side are the rotor angle, rotor speed, and Critical Clearing Time. The proposed model is simulated in MATLAB Simulink and validated in 1 kW hardware setup of grid connected PV system which performs satisfactorily in terms of system parameters and transient stability improvement.

Environmentally friendly power sources are a dependable energy hotspot for our rising energy needs. To outfit the sunlight-based power age. The IoT based sunlight powered charger checking framework is proposed to gather and examines the different elements influencing the sunlight powered charger. The elements are influencing the life-season of sunlight powered charger like temperature, pressure, high voltage and high momentum. It drives temperature of the sunlight powered chargers. Programmed cooling highlight applied with the guide of different boundaries. In the event that the framework detects any strange limit values and it consequently provided the cooling framework into the board. It goes about as insurance safeguard for the sunlight powered chargers.

Research on solar power generation is gaining momentum in recent decade, which requires a costly and complex experimental setup. The Photo-Voltaic (PV) source emulator is a necessary equipment to evaluate Maximum Power Point Tracking (MPPT) algorithm, power converters, and corresponding control algorithm. This paper proposes a novel Neural Network (NN)-based Solar Array Emulator (SAE) to emulate PV array characteristics. The reference model of the proposed SAE has been developed using NN, which can replicate a PV array characteristics with a programmable DC power source's support. A 640 W stand-alone PV array has been designed and tested using the proposed SAE to validate the performance of the developed prototype under different environmental conditions. The results demonstrate that the developed SAE has good accuracy in replicating the PV array characteristics than the conventional diode-based SAE.

Wind turbine sensor fault is considered a critical fault. Maintenance cost of wind energy conversion system increases while turbine sensor faults are unattended. Several fault detections models especially on the bench mark model of wind turbine are available. Bench Mark model defines the wind turbine model mathematically. Support vector machine (SVM) is used to detect the sensor fault in the model. Sensor pairs are used in the turbine to evaluate the fault using data analytics. Measured values from blade pitch, generator and rotor speed sensors are detected for faults. Wind turbine model with the fault detection model is developed using MATLAB to assess the performance of the SVM algorithm. The detection speed, training speed and generalization capability of SVM algorithm enable the use of this algorithm. Finally, the detection model is tested on the DSP28335 to validate the algorithm for real time compatibility. Simulation result approve that the SVM fault detection algorithm with sensor faults executing better speed. Data for training is taken from the simulation carried out for 4400 s to be emulated on the hardware for testing the real time fault detection process.